hypnex-openai (Python)
Drop-in OpenAI client for the Morpheus decentralized inference network (mor.org).
pip install hypnex-openai
Affiliation & monetization
This SDK is published by Hypnex Labs. It is a thin OpenAI-compatible client; calls go directly to api.mor.org and are billed by Morpheus AI to the API-key holder. This SDK does not currently route fees to Hypnex Labs. Hypnex's revenue comes from the sister SDK hypnex-staking (MRC 73 capital referral) and the stake.hypnex.xyz onramp. Hypnex is not affiliated with the Morpheus AI Foundation.
from hypnex_openai import HypnexOpenAI
client = HypnexOpenAI(api_key="mor_...") # get one at https://app.mor.org
response = client.chat.completions.create(
model="mistral-31-24b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
HypnexOpenAI subclasses openai.OpenAI and points it at https://api.mor.org/api/v1. Streaming, tools, async, structured output — all work unchanged.
Models on the Morpheus network
The network exposes 60+ models via OpenAI-compatible endpoints. List them:
hypnex models
Or programmatically:
client.morpheus.active_models() # full registry
client.morpheus.models_by_type("LLM") # filter
client.morpheus.find_model("glm-5") # lookup
Featured LLMs: mistral-31-24b, glm-5, qwen3-235b, qwen3-coder-480b-a35b-instruct, deepseek-r1:70b, minimax-m25. Embeddings: text-embedding-bge-m3. TTS: tts-kokoro. STT: whisper-1.
Drop-in for popular frameworks
Any framework that accepts a base_url accepts Morpheus:
# LangChain
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="qwen3-235b",
api_key=os.environ["HYPNEX_API_KEY"],
base_url="https://api.mor.org/api/v1",
)
# CrewAI
from crewai import LLM
llm = LLM(
model="openai/qwen3-235b",
api_key=os.environ["HYPNEX_API_KEY"],
base_url="https://api.mor.org/api/v1",
)
# llama-index
from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(
model="qwen3-235b",
api_base="https://api.mor.org/api/v1",
api_key=os.environ["HYPNEX_API_KEY"],
is_chat_model=True,
)
# instructor
import instructor
client = instructor.from_openai(HypnexOpenAI())
Morpheus-specific endpoints
client.morpheus.* exposes endpoints that have no OpenAI equivalent:
| Method | What it does |
|---|---|
balance() |
Current MOR balance |
transactions(limit=50) |
Billing history |
spending() |
Cumulative usage |
me() |
User profile |
list_keys() / create_key(name) / delete_key(id) / set_default_key(id) |
API keys |
link_wallet(addr, sig, msg) / get_wallet() / unlink_wallet() |
Wallet binding |
active_models() / find_model(name) / models_by_type(type) |
Public registry |
CLI
hypnex models # list
hypnex health # show api.mor.org health
hypnex chat "Hello" --model glm-5 # one-shot
Async
from hypnex_openai import AsyncHypnexOpenAI
client = AsyncHypnexOpenAI(api_key="mor_...")
r = await client.chat.completions.create(...)
Environment
HYPNEX_API_KEY— your API key (required)HYPNEX_BASE_URL— override base URL (defaulthttps://api.mor.org/api/v1)
Tests
pip install -e ".[dev]"
pytest # public smoke tests
HYPNEX_API_KEY=mor_... pytest # also run authenticated tests
License
MIT
Metadata
Release files for hypnex-openai 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| hypnex_openai-0.1.1.tar.gz | 45.0 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| hypnex_openai-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 55.3 kB
Release files / hypnex_openai-0.1.1.tar.gz
| Download URL | hypnex_openai-0.1.1.tar.gz |
|---|---|
| Size | 45.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
372ed391c8b9d6f45038c7dae3831589eef1bf0d6a4aaf67129d4879cf4eb639
|
|
BLAKE2b-256 checksum How to use checksums |
dfd9cf07dda1c47d748db6e93cc0608c8f6f014461acd9bf9bd0644ba7068164
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / hypnex_openai-0.1.1-py3-none-any.whl
| Download URL | hypnex_openai-0.1.1-py3-none-any.whl |
|---|---|
| Size | 10.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
49f882a2a5be788d4f11a11dd3d5e0d11b1ba1839bd5f7fe217e2024cd1c0ef4
|
|
BLAKE2b-256 checksum How to use checksums |
81da53a1dc27371ae254778bf2e86b3b7ac75826f64bbceeba64859f36b61e1e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for hypnex-openai 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.